AI agents call orgAdmin.queryAuditLog to retrieve information from Gojira without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Audit log querying retrieves historical records about organization activities without creating, modifying, or deleting any data. This is a typical read operation. Severity is low because audit logs are typically informational (though may contain sensitive access patterns), and there are no destructive or financial consequences from querying them. Confidence is high because the intent is unambiguous.
From the tool's definition Tool name includes 'query' and description states 'Query org audit log' — audit log retrieval is a read-only operation with no side effects. The optional filters further indicate data retrieval/filtering rather than modification.
Attacks that exploit this kind of access
Query org audit log with optional filters. It is categorised as a Read tool in the Gojira MCP Server, which means it retrieves data without modifying state.
Register the Gojira MCP server in PolicyLayer and add a rule for orgAdmin.queryAuditLog: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Gojira. Nothing to install.
orgAdmin.queryAuditLog is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the orgAdmin.queryAuditLog rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for orgAdmin.queryAuditLog. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
orgAdmin.queryAuditLog is provided by the Gojira MCP server (windoze95/gojira-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →